Explore skills

特定の GitHub issue への実装着手と PR 作成を依頼されたときに使う。issue 番号・URL・会話内で選んだ issue のいずれかを起点に、実装・commit・lint・受け入れ条件チェック・cross-review・PR 作成・CI 確認まで一気通貫で自動進行する。コードを書いてプルリクを出す作業全般が対象で、issue 選定相談・タイトル編集・クローズ操作・PR レビュー単体には使わない。

Use when the user has NOT yet decided which issue to work on and needs help choosing. This is the pre-decision advisory phase: the user is weighing multiple open issues and wants structured guidance — not implementation. Key triggers: asking which issue to prioritize or tackle next, identifying which issues are blocked vs. ready to start independently, selecting issues that fit limited capacity (s

Performs comprehensive codebase audit checking architecture, tech debt, security vulnerabilities, test coverage, documentation, dependencies, and maintainability. Use when auditing a project, assessing codebase health, running security scans, checking for vulnerabilities, reviewing code quality, analyzing tech debt, or asked to audit/analyze the entire codebase.

Short-form comparison post (X / LinkedIn / Threads). Two things contrasted to reveal a non-obvious preference. Use when the user wants to publish an "X vs Y" take — tools, approaches, mindsets, frameworks — and stake a side. Pairs well after a hot-take or how-to long-form piece.

Destila una guía de estilo de escritura desde 3-5 muestras de referencia y 1-2 textos propios. Genera `scribetronic/style/writing-style.md` con las 8 secciones (voice, structure, sentence-level, signature moves, anti-patterns, ejemplos +, ejemplos -, revision checklist). Usar cuando el usuario quiera crear o refrescar la guía de estilo de su blog/newsletter.

Review database schemas AND in-code data structures for correctness, integrity, performance, scalability, evolvability, simplicity, and design quality. Audits Ecto schemas, Postgres DDL/migrations, dbt models, and application types (Elixir structs/typespecs, TypeScript types). Use when: '/schema-review', 'review this schema', 'review this migration', 'review this data model', 'is this schema sound

Use when rebuilding a scoped section of legacy code clean-room — when the existing implementation is polluting attempts to improve it and a from-scratch rewrite is wanted. Distills the legacy code to pure functional requirements, builds a firewalled greenfield reimplementation that a separate agent designs WITHOUT ever seeing the legacy code, verifies behavioral parity, and optionally cuts over. T

Use this skill when the owner wants to write, draft, or generate a LinkedIn post. Invoke when the user says "write a LinkedIn post", "draft a post for LinkedIn", "create a LinkedIn update", "generate a LinkedIn post", or "post on LinkedIn".

実装・commit 後、`acceptance-check` 通過後・PR 作成前に別の AI (Codex CLI または Claude CLI headless) に diff を渡してセカンドオピニオンのコードレビューを得る。backend は環境変数 `CROSS_REVIEW_BACKEND` で `codex` / `claude-self` から選択でき、未指定時は利用可能な CLI を自動検出する。

Reference guide for npm, pnpm, yarn, and bun package managers. Covers workspace configuration, security audits, troubleshooting, and migration between package managers. Use for complex monorepo setup, debugging package issues, or deep package manager reference.

Reference catalog of canon enforcement principles, epistemological operating rules, metascience diagnostic filters, adversarial validation protocols, and anti-patterns to avoid. Use as a reference when auditing fails, when a new idea conflicts with existing canon, when diagnosing inconsistency, or when user says "anti-patterns", "epistemology", "canon rules", "reasoning principles", "how do I chec

Personal knowledge management framework based on Tiago Forte''s "The PARA Method" and "Building a Second Brain". Use this skill whenever the user is discussing personal knowledge management, note-taking systems, digital organization, or how to turn information into output — even if they do not explicitly say "PARA," "Second Brain," "CODE," or "progressive summarization." Triggers include: (1) orga